Stars
Pier is a Harbor fork built for DeepSWE, with stronger support for CLI agents in air-gapped (no-internet) tasks and more faithful, consistent agent trajectories
Measuring frontier coding agents on original, long-horizon engineering tasks
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Helios - Make your energy visible, in 2.5D in a Lovelace card for Home Assistant
Open benchmark on observability tasks built on Harbor
Framework for evaluating and improving agents
Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps
A visual, non-linear chat interface where conversations are nodes on an infinite canvas
Easily sync code to a remote machine and run commands there. That's it.
Beads - A memory upgrade for your coding agent
Dynamic, adaptive Material Design 3 dashboard for Home Assistant with a transparent, modern aesthetic
Community maintained hardware plugin for vLLM on Apple Silicon
Optimized Ollama LLM server configuration for Mac Studio and other Apple Silicon Macs. Headless setup with automatic startup, resource optimization, and remote management via SSH.
A PostgreSQL Docker container that automatically upgrades your database
SWE-bench: Can Language Models Resolve Real-world Github Issues?
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
A benchmark for evaluating the efficiency of LLM-generated code
Context-Engine MCP - Agentic Context Compression Suite
Jarvis AI Assistant - Voice-powered AI assistant for Mac
Tangle is a web app that allows the users to build and run Machine Learning pipelines without having to set up development environment.
A basic implementation of the OTEL SDK/API for embedded devices such as the Raspberry Pi Pico W, ESP32, and ESP8266
Sparse Contextual Memory Scaffolding - A validated system for continual learning in AI-assisted development
Provider-agnostic, open-source evaluation infrastructure for language models
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.